Twitter roBERTa base This is a RoBERTa base model trained on ~58M tweets on top of the original RoBERTa base checkpoint, as described and evaluated in the TweetEval benchmark (Findings of EMNLP 2020). To evaluate this and other LMs on Twitter specific data, please refer to the Tweeteval official repository. Preprocess Text Replace usernames and links for placeholders: "@user" and "http". Example Masked Language Model Output: Example Tweet Embeddings Output: Example Feature Extraction BibTeX entry and citation info Please cite the reference paper if you use this model.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy